UniMark: Artificial Intelligence Generated Content Identification Toolkit

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Meilin, He, Ji, Yu, Yi, Xu, Jia, Lei, Shanzhe, Teng, Yan, Wang, Yingchun, Wang, Xuhong
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910095794765824
author Li, Meilin
He, Ji
Yu, Yi
Xu, Jia
Lei, Shanzhe
Teng, Yan
Wang, Yingchun
Wang, Xuhong
author_facet Li, Meilin
He, Ji
Yu, Yi
Xu, Jia
Lei, Shanzhe
Teng, Yan
Wang, Yingchun
Wang, Xuhong
contents The rapid proliferation of Artificial Intelligence Generated Content has precipitated a crisis of trust and urgent regulatory demands. However, existing identification tools suffer from fragmentation and a lack of support for visible compliance marking. To address these gaps, we introduce the \textbf{UniMark}, an open-source, unified framework for multimodal content governance. Our system features a modular unified engine that abstracts complexities across text, image, audio, and video modalities. Crucially, we propose a novel dual-operation strategy, natively supporting both \emph{Hidden Watermarking} for copyright protection and \emph{Visible Marking} for regulatory compliance. Furthermore, we establish a standardized evaluation framework with three specialized benchmarks (Image/Video/Audio-Bench) to ensure rigorous performance assessment. This toolkit bridges the gap between advanced algorithms and engineering implementation, fostering a more transparent and secure digital ecosystem.
format Preprint
id arxiv_https___arxiv_org_abs_2512_12324
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniMark: Artificial Intelligence Generated Content Identification Toolkit
Li, Meilin
He, Ji
Yu, Yi
Xu, Jia
Lei, Shanzhe
Teng, Yan
Wang, Yingchun
Wang, Xuhong
Cryptography and Security
Artificial Intelligence
The rapid proliferation of Artificial Intelligence Generated Content has precipitated a crisis of trust and urgent regulatory demands. However, existing identification tools suffer from fragmentation and a lack of support for visible compliance marking. To address these gaps, we introduce the \textbf{UniMark}, an open-source, unified framework for multimodal content governance. Our system features a modular unified engine that abstracts complexities across text, image, audio, and video modalities. Crucially, we propose a novel dual-operation strategy, natively supporting both \emph{Hidden Watermarking} for copyright protection and \emph{Visible Marking} for regulatory compliance. Furthermore, we establish a standardized evaluation framework with three specialized benchmarks (Image/Video/Audio-Bench) to ensure rigorous performance assessment. This toolkit bridges the gap between advanced algorithms and engineering implementation, fostering a more transparent and secure digital ecosystem.
title UniMark: Artificial Intelligence Generated Content Identification Toolkit
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2512.12324